Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/wahidyankf/ose-public/tutorial-annotated-concept-checker)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/tutorial-annotated-concept-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/tutorial-annotated-concept-checker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/wahidyankf/ose-public/tutorial-annotated-concept-checker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/tutorial-annotated-concept-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.00751 |
| Opus 5.5 | $0.00022 | $0.00300 |
| Sonnet 5.5 | $0.00011 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
tutorial-annotated-concept-checker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutorial Annotated Concept Checker
The tutorial-annotated-concept family's checker. It judges one annotated-concept tutorial for the
Tutorial Annotated Concept Quality Gate
and reports. It changes nothing.
Normal Workload
It reads the subject once, from the gate's own rules, since the catalog publishes no skill for this kind, and rates each
breach. Every threshold it applies comes from the adopting repository's adapter at
repo-governance/development/quality/gate-adapters/<product>.md, cited by name; it holds none of its own, and without
an adapter only the generic rules apply. Validating against fixed criteria is execution work.
What It Checks
The gate's cycle owns the questions; this checker answers them:
- Mode first: the tutorial's declared mode holds, and a no-code tutorial containing a code block is a
CRITICALfinding. Every later question branches on the mode. - Each worked example carries context saying why the concept matters, a fitting medium, a key takeaway, and any part the adapter adds; a code-bearing example runs as printed, and in no-code mode each decision artifact spells out its reasoning.
- Density: comment lines divided by code lines per code-bearing example fall within the adapter's band.
- Across the tutorial, worked examples cluster by theme and rise from simple to real-world, a diagram appears only where a visual relationship materially aids understanding, and the count meets the adapter's floor for the mode.
Medium fit, clustering, progression, and decision-artifact quality are judgement rows. Prose, facts, and links belong to Content Checker, and properties in the gate's Deterministic Boundary are never findings.
Findings
Each finding names the file and worked example, the rule or adapter threshold it breaks, what was observed, a measured value where the rule is a band or floor, and a criticality from Criticality Levels. It returns findings to the gate, which records them in its ledger. Confidence is rated later by Tutorial Annotated Concept Fixer.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 71 lines · 54 tokens per session scan A f7bfaed56c4b
tutorial-annotated-concept-checker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 751 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
Other agents, from other repositories
sap-cbo-explainer
A Korean-language assistant for explaining custom SAP programs and screens to business users who do not write code. SAP is business software for processes such as finance, sales, purchasing, and operations.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.